Expert System Design for Diagnosis of Diseases for Paddy Crop

Expert System Design for Diagnosis of Diseases for Paddy Crop

Sreekantha Desai Karanam (NMAM Institute of Technology, India) and Deepthi M. B. (NMAM Institute of Technology, India)
DOI: 10.4018/978-1-5225-9632-5.ch003

Abstract

India has the second largest area of arable (agricultural) land on this earth with heterogeneous agroclimatic regions across the country. India has the potential to grow a wide range of agricultural crops and varied raw material base for food processing industry. The paddy crop yield/hector of land is highest in Egypt is 9.5, while India is producing only 2.9. India's lower paddy crop productivity/hector and higher cost of production is a major concern for farmers. There are various reasons for India's low paddy crop yield, such as lack of mechanization, not adopting to modern method of farming, small land holdings, poor pests, and disease management. The recent survey discovered that there is huge gap in demand and supply in crop production and is likely to hit more than 15% by 2020, with the gap worsening to 20-25% by 2025. Researchers aimed to address this low crop yield issue by designing an expert system. This expert system helps the farmers by identifying and predicting the diseases for paddy crop to enhance crop yield and to reduce the supply and demand gap.
Chapter Preview
Top

Review Of Literature

The precise identification of paddy crop diseases and pests is very essential for enhancing the rice crop yield and quality cultivation (Peng et al., 2010). The process of diagnosis of paddy crop diseases is very complex. Authors have applied Back Propagation Algorithm (BPA) of neural network technology to design an expert system for diagnosis of diseases, which is more efficient in processing incomplete and vague information. Authors (Li, Zhang & Yang, 2012) have proposed the characteristics of hybrid approach, such as self-learning ability of neutral network, inference ability of fuzzy systems and knowledgebase of expert system for prediction of crop growth. Authors have analysed growth rate of crop and the performance of expert systems using simulation and testing. The results obtained demonstrated that this practice is effective in the high crop yield management and better quality. Authors (Kaur, Singh Rekhi & Nayyar, 2013) have discovered that currently majority of Fortune 1000 companies are developing expert systems for enhancing the quality, efficiency and competitive leverage in their day to day operations. The expert systems are being used in scientific, business and industrial applications such as, to discover oil or mineral deposits, control various space crafts and diagnosing medical diseases.

Complete Chapter List

Search this Book:
Reset